Variational Autoencoders for P-wave Detection on Strong Motion Earthquake Spectrograms

TL;DR

This paper explores how different Variational Autoencoder architectures affect P-wave detection in noisy earthquake spectrograms, highlighting the importance of global context mechanisms for effective self-supervised anomaly detection.

Contribution

It systematically evaluates 492 VAE configurations, demonstrating that attention mechanisms improve P-wave detection by emphasizing global context over reconstruction accuracy.

Findings

Attention mechanisms yield highest detection performance (AUC 0.875).

Skip connections minimize reconstruction error but cause overgeneralization.

Attention-based VAE achieves AUC 0.91 in near-source detection.

Abstract

Accurate P-wave detection is critical for earthquake early warning, yet strong-motion records pose challenges due to high noise levels, limited labeled data, and complex waveform characteristics. This study reframes P-wave arrival detection as a self-supervised anomaly detection task to evaluate how architectural variations regulate the trade-off between reconstruction fidelity and anomaly discrimination. Through a comprehensive grid search of 492 Variational Autoencoder configurations, we show that while skip connections minimize reconstruction error (Mean Absolute Error approximately 0.0012), they induce "overgeneralization", allowing the model to reconstruct noise and masking the detection signal. In contrast, attention mechanisms prioritize global context over local detail and yield the highest detection performance with an area-under-the-curve of 0.875. The attention-based Variational Autoencoder achieves an area-under-the-curve of 0.91 in the 0 to 40-kilometer near-source range, demonstrating high suitability for immediate early warning applications. These findings establish that architectural constraints favoring global context over pixel-perfect reconstruction are essential for robust, self-supervised P-wave detection.